检索结果-内蒙古大学图书馆

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Wu, Chengpei Lou, Yang Li, Junli College of Computer Science Sichuan Normal University Chengdu610066 China Key Laboratory of System Control and Information Processing Ministry of Education Shanghai200240 China National Yang Ming Chiao Tung University Department of Computer Science Hsinchu300 Taiwan Graduate School of Information Science and Technology Osaka University Osaka565-0871 Japan

ISBN: (纸本)9798350337020

Many natural and engineering systems can be modeled and represented in the forms of graph data, and then studied using graph theory and network analysis tools. Graph representation learning aims at generating lower-dimensional representations from higher-dimensional graph data, which is a crucial step that facilitates the follow-up tasks, such as node and graph classifications. In this paper, we present a simple but effective graph representation learning method, namely the pyramid pooling-based local profile (PPLP), which enables local nodal profiles to be transformed into a graph representation, with multi-scale features extracted. PPLP can be either embedded into a graph neural network as the readout layer, or perform independently as a graph embedding algorithm. The resultant representations of PPLP are for graph-level tasks. PPLP is experimentally tested by performing graph classification tasks on ten representative datasets, either as the readout layer of different graph neural networks, or as an independent graph embedding algorithm. Experimental results demonstrate that: 1) when embedded into graph neural networks, PPLP outperforms the widely-used global pooling-based readout methods;2) as an independent graph embedding algorithm, PPLP performs fairly good, especially on the social network datasets. The investigation confirms PPLP as a simple but promising method for graph-level tasks. © 2023 IEEE.

关键词： graph classification graph neural network Graph representation learning pyramid pooling

来源：评论

学校读者我要写书评

暂无评论

Domain Adaptation-based Radio Frequency Fingerprint Identification for Industrial Cyber-Physical systems

引用

IEEE Network 2025年

作者： Wang, Yatong Cao, Bin Wen, Zhongyi Yan, Mu Song, Changqing Beijing Institute of Technology School of Information and Electronics Beijing100081 China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Technology Beijing100191 China University of Electronic Science and Technology of China National Key Laboratory of Wireless Communications Chengdu611731 China Laboratory of Electromagnetic Space Cognition and Intelligent Control Beijing100191 China

With the widespread adoption of cloud and fog platforms, security issues facing Industrial Cyber-Physical systems (ICPSs) are increasingly prominent. Radio Frequency Fingerprinting (RFFI) emerges as a promising physical layer security technique for user authentication, effectively enhancing ICPS security over wireless networks by exploiting inherenthardware imperfections in transmitters. However, as technologies evolve and user environments become denser and more complex, existing RFFI techniques encounter significant domain shift challenges, leading to performance degradation. Therefore, developing domain-adaptive RFFI techniques is crucial for the effectiveness of ICPSs. In this article, we first provide a comprehensive review of the RFFI framework, emphasizing its applications in ICPSs and the key processes involved. Next, we focus on the domain shift issues faced by RFFI in ICPSs and present a comprehensive survey of domain adaptation methods. To tackle these challenges, we propose a novel feature-alignment based domain adaptation (FADA) framework for RFFI, which is designed to mitigate the performance degradation caused bycross-domain shifts by aligning the feature representations of the source and target domain. Finally, we discuss the inherent challenges and future directions for developing domain adaptation based RFFI to enhance the security of ICPSs. © 2025 IEEE. All rights reserved.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

S2KAN-SLAM: Elastic Neural LiDAR SLAM with SDF Submaps and Kolmogorov-Arnold Networks

引用

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Wang, Zhong Zhang, Lin Wang, Hesheng Shanghai Jiao Tong University State Key Laboratory of Avionics Integration and Aviation System-of-Systems Synthesis Department of Automation Key Laboratory of System Control and Information Processing of Ministry of Education Shanghai200240 China Tongji University School of Computer Science and Technology National Pilot Software Engineering School with Chinese Characteristics Shanghai201804 China

Traditional LiDAR SLAM approaches prioritize localization over mapping, yet high-precision dense maps are essential for numerous applications involving intelligent agents. Recent advancements have introduced methods leveraging neural fields to enhance mapping capabilities;however, these approaches still face several limitations. Firstly, concerning scene representation, they typically employ neural fields with high-dimensional features and multi-layer perceptron decoders utilizing non-continuous activation functions. This results in low learning efficiency and challenges in capturing high-frequency signals. Secondly, in terms of scene organization, these methods often treat the entire scene as a singular neural field, leading to inefficiencies, inflexibility, and difficulties in rectifying accumulated errors when mapping large-scale environments over extended periods. To tackle the first issue, we propose a lightweight continuous SDF regression approach by encoding the scene in single-valued embeddings and decoding SDF values from a Kolmogorov-Arnold Network. By minimizing discrepancies in measuring range, sampling distance, and decoded SDF values, we facilitate iterative frame-to-model tracking and bundle adjustment neural mapping. To mitigate the second challenge, we propose structuring the whole scene into multiple neural SDF submaps. By establishing node-node, node-submap, and loop closure constraints into a global pose graph, the system can create dense neural maps with global consistency across large-scale scenes. Experimental evaluations in both real-world and simulated settings indicate that our system achieves superior mapping completeness and accuracy, enhanced learning efficiency, reduced memory consumption, and greater flexibility compared to its counterparts. © 2025 IEEE.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Perceptual Attribute Analysis of Objective Acoustic Parameters of Musical Instrument Timbre

Perceptual Attribute Analysis of Objective Acoustic Paramete...

引用

2021 International Conference on Culture-Oriented Science and technology, ICCST 2021

作者： Liu, Jingyu Chen, Yuqu Ran, Can Huang, Yongzhan Jiang, Wei Ministry of Culture and Tourism Communication University of China Key Laboratory of Acoustic Visual Technology and Intelligent Control System Beijing China Communication University of China School of Information and Communication Engineering Beijing China

ISBN: (纸本)9781665442541

The timbre attributes are affected by multiple factors such as the time domain, frequency domain, time-frequency domain, and harmonic structure of the sound signal, and there is a certain degree of correlation and redundancy among the objective acoustic parameters. Analyzing the perception of the objective acoustic parameters of the timbre Attributes is of great significance to the study of timbre perception. In order to achieve the above goals, this paper constructs a timbre database of Chinese and Western musical monophonic instruments, and extracts 45 timbre objective acoustic parameters based on this database. through factor analysis of these acoustic parameters, it shows that the information of 45 timbre objective acoustic parameters can be condensed into 6 factors, and each factor has a clear timbre perception attribute. Based on this result, we use the multi-dimensional scale analysis method to verify the six factors, and the verification results are basically consistent with the factor analysis results. The 6 factors constructed can explain the time-frequency domain distribution, structure and energy distribution of acoustic parameters, and provide a theoretical basis for constructing an interpretable model based on audio objective acoustic parameters. © 2021 IEEE.

关键词： Multivariant analysis

来源：评论

学校读者我要写书评

暂无评论

Tensor and Minimum Connected Dominating Set based Confident information Coverage Reliability Evaluation for IoT

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2024年第03期10卷 547-561页

作者： Xiao, Ziheng Zhu, Chenlu Feng, Wei Liu, Shenghao Deng, Xianjun Lu, Hongwei Yang, Laurence T. Park, Jong Hyuk Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China Artificial Intelligence and Intelligent Transportation Joint Technical Center of HUST and Hubei Chutian Intelligent Transportation Company Ltd United States Network and Industrial Control Information Security Technology Department China Nuclear Power Operation Technology Company Ltd. 1011 Xiongchu Avenue Hubei Wuhan430070 China The Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of

Internet of Things (IoT) reliability evaluation contributes to the sustainable computing and enhanced stability of the network. Previous algorithms usually evaluate the reliability of IoT by enumenating the states of nodes and networks, which are difficult to handle IoT with hundreds of nodes because the computational cost. In this paper, a novel algorithm, TMCRA, is proposed to evaluate the reliability of IoT in complex network environment, which consider both coverage and connectivity. For coverage, TMCRA employs the Confident information Coverage (CIC) model to divide the target area into independent grids and calculates the coverage rate. In terms of connectivity, TMCRA forming the Virtual Backbone Network (VBN) based on two proposed methods: TMA and MGIN, and evaluate connectivity by analyzing the VBN rather than the whole network. The TMA and MGIN are two algorithms for constructing Minimum Connected Dominant Sets (MCDS), which are suitable for different scale networks. Finally, based on the data of coverage and connectivity, TMCRA utilizes tensors for the unified modeling and representation of network structure, and calculates IoT reliability based on the tensors. Simulations are carried out for various sizes of IoT to show the advantages and effectiveness of the proposed approach in reliability evaluation. © 2016 IEEE.

关键词： Data reliability

来源：评论

学校读者我要写书评

暂无评论

An image enhancement algorithm based on multi-scale Retinex theory to improve the images quality of sensors 12

An image enhancement algorithm based on multi-scale Retinex ...

引用

SPIE 12th International Symposium on Multispectral Image Processing and Pattern Recognition, MIPPR 2023

作者： Li, Yiyao Chen, Zhong Sun, Wenyuan School of Journalism and Communication Central China Normal University Luoyu Road 152 Wuhan China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Luoyu Road 1037 Wuhan China National Key Laboratory of Science and Technology on Multi-spectral Information Processing Luoyu Road 1037 Wuhan China Key Laboratory of Ministry of Education for Image Processing and Intelligent Control Luoyu Road 1037 Wuhan China Central China Normal University Library Luoyu Road 152 Wuhan China

ISBN: (数字)9781510674967

ISBN: (纸本)9781510674950

Nowadays, image recognition plays a pivotal role in acquiring data via sensors. However, the adaptability of traditional algorithms is hindered by the unpredictable nature of open environments, varying sensor quality, and image dimensions. Challenges arise in adverse conditions like inclement weather, low light, and optical distortions. Retinex-based methods have emerged as a viable solution, effectively enhancing images plagued by shadows or poor lighting. Yet, issues surface when images possess saturated colors;the conventional multi-scale Retinex with color restoration risks color inversion. Moreover, during gain compensation, extreme histogram values occupy significant gray level space, obscuring vital image details. This study delves into these challenges and proposes an enhanced multi-scale Retinex algorithm. Our approach substitutes logarithmic functions with tansig functions, eliminating color inversion risks. Additionally, a novel gain compensation method, integrating histogram stretching with Gamma correction, refines image clarity. The algorithm's robustness is evidenced in diverse scenarios, including adverse weather, low light, underwater imaging, and non-uniform lighting. Experimental results validate our method's superiority, surpassing other Retinex-based techniques both qualitatively and quantitatively. This research contributes valuable insights into image enhancement methodologies, fostering advancements in sensor-based data gathering in Smart Spaces. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Robot map construction based on topology and hierarchical fusion in unknown environment 2

Robot map construction based on topology and hierarchical fu...

引用

2nd International Conference on the Frontiers of Intelligent control, Measurement, and Signal systems, FICMSS 2025

作者： Li, Zirun Zhu, Chunjia Tao, Hao Zhang, Qingfang Pu, Chenyu Xiao, Jinsheng School of Electronic Information Wuhan University Wuhan430072 China China Ship Development and Design Center Hubei Wuhan430064 China National Key Laboratory of Information System and Technology Beijing Institute of Control and Electronic Technology Beijing100038 China

Map construction has always been crucial in exploring enclosed unknown environments. Traditional mapping methods have problems such as low accuracy or long time consumption. Due to the indoor and enclosed nature of unknown environments, inspection robots often encounter challenges in mapping and path planning. To address similar issues, we proposed an optimized indoor mapping solution based on topology technology and hierarchical fusion, and conducted experiments using robots in a library simulation scenario in an unknown environment. Figure 1 shows the map that we have obtained by layering and *** utilizing topology techniques and hierarchical fusion mapping methods, we have effectively simplified the mapping process, reducing computational complexity and cost while obtaining spatial information and this method allows for the consideration of the geometric characteristics of robots when planning safe and accurate passable paths. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Sensitivity and Distance Based Performance Analysis for Batteryless Tags with Transmit Beamforming and Ambient Backscattering

引用

China communications 2022年第2期19卷 109-117页

作者： Minzheng Jia Chaochao Yao Wei Liu Ruyi Ye Tutun Juhana Bo Ai Department of Information Engineering Beijing Polytechnic CollegeBeijing 100042China School of Computer and Information Technology Beijing Jiaotong UniversityBeijing 100044China School of Communication and Information Engineering Xi’an University of Posts and TelecommunicationsXi’an 710121China Chinese National Institute of Standalization Beijing 100088China School of Electrical Engineering and Informatics Institut Teknologi BandungIndonesia State Key Laboratory of Rail Traffic Control and Safety Beijing Jiaotong UniversityBeijing 100044China

Ambient backscatter is a new green technology for Internet of Things(IoT)that utilizes surrounding wireless signals to enable batteryless devices to communicate with other *** battery-free devices first harvest energy from ambient wireless signals and then backscatter the signals for ***,sensitivity and distance are two important parameters for system ***,most existing studies on ambient backscatter communication systems do not consider the impact of the sensitivity of the energy-harvesting nodes and the distances between these *** this paper,we first provide a literature review for ambient communication technology and then take sensitivity and distance as two key parameters and investigate the sensitivity and distance based performance for ambient backscatter communication ***,we establish the mathematical model based on distances between transceivers and backscattering nodes,extract a parameter that can differentiate the direct path and the backscattering path,evaluate the effects of transmit beamforming,design an energy detector for the reader,and analyze the outage probability of energy harvesting at the tag and the bit error rate(BER)at the *** are then provided to corroborate the proposed studies.

关键词： ambient backscatter battery-free tag Internet of Things(IoT) outage probability performance analysis sensitivity transmission distance

来源：评论

学校读者我要写书评

暂无评论

Emission Evaluation for Diesel Vehicles under Typical Operating Conditions 8

Emission Evaluation for Diesel Vehicles under Typical Operat...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Li, Jiaren Xu, Zhenyi Cao, Yang Xia, Xiushan Kang, Yu Anhui University AHU-IAI AI Joint Laboratory Hefei230601 China Ministry of Education Key Laboratory of System Control and Information Processing Shanghai200240 China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei230088 China University of Science and Technology of China Department of Automation Hefei230026 China Institute of Advanced Technology University of Science and Technology of China Hefei230088 China

ISBN: (纸本)9798350300178

China's ambient air quality has improved significantly as a result of the formulation and implementation of the Action Plan for the Prevention and control of Air Pollution and the Three-Year Action Plan for Winning the Blue Sky Defense War, but the air pollution problem in key regions remains severe, diesel truck pollution has not been effectively addressed, and mobile sources are an important source of nitrogen oxide emissions. The existing diesel vehicle emission model is primarily divided based on average vehicle speed and VSP binning methods, and it lacks an instantaneous vehicle speed model. This paper collected data from 10 diesel vehicles in order to accurately evaluate driving conditions and promote energy saving and emission reduction of heavy-duty diesel vehicles. Then we extracted 51,925 kinematic fragment data after cleaning abnormal data and built a kinematic feature evaluation system of diesel vehicles closely related to NOx emission. The sample data of kinematic segments were clustered into two groups of low-speed conditions and medium-speed conditions using the standardized mutual information to extract the characteristics with strong correlation with NOx and the vehicle driving conditions assessment model of cluster analysis. From the clustering results, the high NOx emission is completely classified into the low-speed working condition, which matches the conclusion that the high NOx emission region appears in the low-speed acceleration region reached by previous researchers through experimental studies, indicating that the kinematic feature evaluation model of diesel vehicles established in this paper is reasonable and effective. © 2023 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Application and Performance Evaluation of Object Detection technology Based on Computer Vision

Application and Performance Evaluation of Object Detection T...

引用

Asian control Conference

作者： WeiXue Li Hang Zhang Cong Wan JiaWen Shi TingRu Li National Key Laboratory of Complex System Control and Intelligent Agent Cooperation Beijing China Talent Exchange Center Ministry of Industry and Information Technology P.R.C. Beijing China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

In light of the challenges posed by the variability of industrial part shapes, weak texture information, and surface reflections in current industrial vision inspection, traditional methods such as feature descriptors and template matching are inadequate. This paper innovatively proposes a machine learning object detection method, establishes robust stable features for weakly textured industrial parts, and evaluates the performance of the model and feature selection in combination with actual fuel tank cap detection tasks. Firstly, we construct a dataset of fuel tank cap targets and establish a comprehensive and relatively stable feature dataset, including geometric features, texture features, and color features. Secondly, through ablation experiments and comparative experiments, we conduct intelligent per-formance testing on model detection accuracy, parameter selection, and feature contribution. Finally, the evaluation results demon-strate that the support vector machine (SVM) model exhibits the best detection performance after feature selection, with a detection accuracy of 99.0% under the optimal parameter settings validated through experiments.

关键词： Support vector machines Adaptation models Image color analysis Computational modeling Fuel storage Object detection Inspection

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：